© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 10199
    Prev
    Next
    INDEX
    Explanations

    references to where the money or income generated from sales or transactions is directed or used

    oai_token-act-pair · gpt-3.5-turbo

    references to financial gains or revenue from various sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Leica
    -0.68
    ndra
    -0.66
     Cabin
    -0.65
    tem
    -0.65
     Nem
    -0.65
     Faces
    -0.65
     loudspe
    -0.64
     Mirror
    -0.64
     Cherry
    -0.64
     Rear
    -0.64
    POSITIVE LOGITS
     proceeds
    1.32
     Proceed
    1.09
    interstitial
    0.85
     receipts
    0.84
    atinum
    0.83
     "$:/
    0.79
    wikipedia
    0.77
     ($)
    0.77
    ĸļ
    0.75
     profits
    0.75
    Activations Density 0.017%

    No Known Activations